Women in Work Force

#Importing Data Set
ss14pusa = read.csv(file.choose(),header=TRUE)  # read csv file
ss14pusb = read.csv(file.choose(),header=TRUE)

#Libraries
require(plyr)
require(dplyr)
require(rbokeh)
require(ggplot2)

#Importing Data Set in a faster way
library(data.table)
variables=c("SEX","OCCP","WKHP","MAR","WAGP","SCHL","ESP","RAC1P","ST","PAOC","PWGTP")
ss14pusa=fread("~/Google Drive/Data for R/csv_pus/ss14pusa.csv",head=TRUE,select=variables)
ss14pusb=fread("~/Google Drive/Data for R/csv_pus/ss14pusb.csv",head=TRUE,select=variables)

attach(ss14pusa)
names(ss14pusa)
<<<<<<< HEAD
ss14pusa_edit = data.frame(SEX,OCCP,WKHP,MAR,WAGP,SCHL,ESP, RAC1P, ST, PAOC, PWGTP, AGEP)
detach(ss14pusa)

attach(ss14pusb)
ss14pusb_edit = data.frame(SEX,OCCP,WKHP,MAR,WAGP,SCHL,ESP, RAC1P, ST, PAOC, PWGTP, AGEP)
=======
ss14pusa_edit = data.frame(SEX,OCCP,WKHP,MAR,WAGP,SCHL,ESP, RAC1P, ST, PAOC, PWGTP)
detach(ss14pusa)

attach(ss14pusb)
ss14pusb_edit = data.frame(SEX,OCCP,WKHP,MAR,WAGP,SCHL,ESP, RAC1P, ST, PAOC, PWGTP)
>>>>>>> master
detach(ss14pusb)

Data = rbind(ss14pusa_edit,ss14pusb_edit)
colnames(Data) <- c("Gender","Occupation", "Work_hours", "Marriage", "Income", "Education" ,"Parental_Occupation", "Race", "State", "Children", "Weight", "Age")


write.csv(Data, file = "Data.csv",row.names=TRUE)

#Delete income=0/NA rows
row_to_keep=which(Data$Income>0)
Data=Data[row_to_keep,]

#Recode Region
#https://en.wikipedia.org/wiki/List_of_regions_of_the_United_States#/media/File:Census_Regions_and_Division_of_the_United_States.svg
<<<<<<< HEAD
Data$Region <- recode(Data$State,c(09,23,25,33,44,59,34,36,42)='Northeast';c(17,18,26,38,55,19,20,27,29,31,38,46)='Mid West'; c(10,12,13,24,37,45,51,11,54,01,21,28,47,05,22,40,48)='South';c(04,08,16,30,32,35,49,50,02,06,15,41,53)='West'))
=======
require(car)
Data$Region <- recode(Data$State,"c(09,23,25,33,44,59,34,36,42)='Northeast';c(17,18,26,38,55,19,20,27,29,31,38,46,39)='Midwest'; c(10,12,13,24,37,45,51,11,54,01,21,28,47,05,22,40,48)='South';c(04,08,16,30,32,35,49,50,02,06,15,41,53,56)='West';'72'='Puerto Rico'")

# Recode Division
Data$Division <- recode(Data$State,"c(53,41,6,2,15)='Pacific';c(4,8,16,30,32,35,49,56)='Mountain'; c(19,20,27,29,31,38,46)='West North Central';c(17,18,26,39,55)='East North Central';c(5,22,40,48)='West South Central';c(1,21,28,47)='East South Central';c(34,36,42)='Middle Atlantic';c(10,11,12,13,24,37,45,51,54)='South Atlantic';c(9,23,25,33,44,50)='New England'")

master

#Recode Education
Data$Education <- recode(Data$Education,"c(01,02,03,04,05,06,07,08,09,10,11)='~greade8';c(12,13,14,15,16,17,18,19)='grade9~college_nodegree';c(20,21)='associate/bachelor';c(22,23)='master/professional';c(24)='doctor')")

#Recode Marriage
Data$Marriage <- as.factor(Data$Marriage)
levels(Data$Marriage) <- c("Married", "Widowed", "Divorced", "Seperated", "Never Married")

#Recode Education
library(car)
Data$Education <- recode(Data$Education,"1:11='~greade8';12:19='grade9~college_nodegree';20:21='associate/bachelor';22:23='master/professional';24='doctor'")

summary(lm(MEAN ~ Marriage + Age, data = Data_wed_SCI))

Managers

Women_MGR<-filter(Data_women, Occupation ==“MGR”) Data_wed_MGR <- ddply(Women_MGR, .(Marriage, Age), summarise, MEAN = weighted.mean(Income, Weight, na.rm = T))

ggplot(Data_wed_MGR,aes(y = MEAN, x =Age,colour=Marriage,shape=Marriage)) + geom_point() + geom_smooth(method=“loess”, fill=NA)

mgr <- figure(width = NULL, height = NULL) %>% ly_points(Age, MEAN, data = Data_wed_MGR, color = Marriage, glyph = as.factor(Marriage), hover = list(Marriage, Age)) mgr

Lawyers

Women_LGL<-filter(Data_women, Occupation ==“LGL”) Data_wed_LGL <- ddply(Women_LGL, .(Marriage, Age), summarise, MEAN = weighted.mean(Income, Weight, na.rm = T))

ggplot(Data_wed_LGL,aes(y = MEAN, x =Age,colour=Marriage,shape=Marriage)) + geom_point() + geom_smooth(method=“loess”, fill=NA)

lgl <- figure(width = NULL, height = NULL) %>% ly_points(Age, MEAN, data = Data_wed_LGL, color = Marriage, glyph = as.factor(Marriage), hover = list(Marriage, Age)) lgl

summary(lm(MEAN ~ Marriage + Age, data = Data_wed_LGL))

Business

Women_BUS<-filter(Data_women, Occupation ==“BUS”) Data_wed_BUS <- ddply(Women_BUS, .(Marriage, Age), summarise, MEAN = weighted.mean(Income, Weight, na.rm = T))

ggplot(Data_wed_BUS,aes(y = MEAN, x =Age,colour=Marriage,shape=Marriage)) + geom_point() + geom_smooth(method=“loess”, fill=NA)

bus <- figure(width = NULL, height = NULL) %>% ly_points(Age, MEAN, data = Data_wed_BUS, color = Marriage, hover = list(Marriage, Age)) bus

summary(lm(MEAN ~ Marriage + Age, data = Data_wed_BUS))

Computer

Women_CMM<-filter(Data_women, Occupation ==“CMM”) Data_wed_CMM <- ddply(Women_CMM, .(Marriage, Age), summarise, MEAN = weighted.mean(Income, Weight, na.rm = T))

ggplot(Data_wed_CMM,aes(y = MEAN, x =Age,colour=Marriage,shape=Marriage)) + geom_point() + geom_smooth(method=“loess”, fill=NA)

cmm <- figure(width = NULL, height = NULL) %>% ly_points(Age, MEAN, data = Data_wed_CMM, color = Marriage, hover = list(Marriage, Age))

cmm

summary(lm(MEAN ~ Marriage + Age, data = Data_wed_CMM))

bounds <- range(c(Data_wed_occp\(Marriage, Data_wed_occp\)MEAN ))

grid_plot(lapply(split(Data_wed_occp, as.factor(Data_wed_occp$Occupation)), function(d) { figure(width = 300, height = 350) %>% ly_points(Age, MEAN, data = Data_wed_occp, color = Marriage, hover = list(Marriage, Age)) }), nrow = 2, same_axes = TRUE)

ggplot(Data_wed_occp,aes(x = factor(Occupation), fill = factor(Marriage), y = MEAN)) + geom_bar(stat = “identity”) + geom_text(position = “stack”,aes(y = MEAN, label = Marriage), size = 2, check_overlap = TRUE)

require(plotly) p <- plot_ly(Data_wed_occp, x = Age, y = MEAN,group = Occupation, text = paste(“Clarity:”, Age), mode = “markers”, xaxis = paste0(“x”, Occupation), symbol = Marriage, jitter = .9)

p<- subplot(p) ``` ???

master

MotherWorking=select(Data_women, Income,Children,Work_hours)
#detach(package:plyr)
GroupedMotherWorking <-
  MotherWorking %>%
  na.omit() %>%
  group_by(Children,Work_hours) %>% 
  summarize(
    AvgIncome = mean(Income),
    count=n()
  ) 

library(plotly)
# note how size is automatically scaled and added as hover text

plot_ly(GroupedMotherWorking, x = Work_hours, y = AvgIncome,size=sqrt(count), color = Children,text = paste("Count: ", count),opacity=1-Children*0.2,mode = "markers")

#plot_ly(GroupedMotherWorking, x = Work_hours, y = AvgIncome, text = paste("Count: ", #count),mode = "markers", opacity=1-Children*0.2,color = Children)

Observations: 1. When work_hours smaller than 60Hrs, Avg Income tend to be positively related to work hour. 2. There are generally more females with no Children 3. Females with Children from 6 to 17 often has higher avg income

ggplotly(p)

ggplotly(p)

Error in file(file, ifelse(append, "a", "w")) : 
  cannot open the connection

Observations: 1. Females with Children from 6 to 17 usually tend to have higher average income as the dot has darker color. 2. Occupation of ENG, MGR and CMM usually tend to have higher salary. On the other hand, female in LGL field always have lower salary 3.

From the graphs we see that the Northeast region, especially the New England Division, has higher income level than other parts of the States. The next question is why it happens, e.g. particular popular high-income occupations in certain regions?